Related papers: Breaking Bad Tokens: Detoxification of LLMs Using …
Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model…
Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder-Denoised Concept Vectors (SDCV), which selectively keep the…
Sparse autoencoders (SAEs) are a popular method for decomposing Large Langage Models (LLM) activations into interpretable latents. However, due to their substantial training cost, most academic research uses open-source SAEs which are only…
Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications. To…
Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting language model activations by decomposing them into sparse, interpretable features. A popular approach is the TopK SAE, that uses a fixed number of the most active…
Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern. With the advent of multilingual S/LLMs, the question now becomes a matter of scale:…
Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…
Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In…
Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…
Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…
Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…
Detecting life-threatening language is essential for safeguarding individuals in distress, promoting mental health and well-being, and preventing potential harm and loss of life. This paper presents an effective approach to identifying…
Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely opaque. In this work, we present Sparse Autoencoder For…
Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public trust. Existing toxicity mitigation approaches primarily…
Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…
Large Language Models (LLM) have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel…
Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…